The repo contains the residual-SqueezeNet, which is obtained by
adding bypass layer to SqueezeNet_v1.0. Residual-SqueezeNet improves the
top-1 accuracy of SqueezeNet by 2.9% on ImageNet without changing the
model size(only 4.8MB).
If you find residual-SqueezeNet useful in your research, please consider citing the paper:
@article{SqueezeNet,
title={SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and< 0.5MB model size},
author={Iandola, Forrest N and Han, Song and Moskewicz, Matthew W and Ashraf, Khalid and Dally, William J and Keutzer, Kurt},
journal={arXiv preprint arXiv:1602.07360},
year={2016}
}
Usage
$CAFFE_ROOT/build/tools/caffe test --model=trainval.prototxt --weights=SqueezeNet_residual_top1_0.6038_top5_0.8250.caffemodel --iterations=1000 --gpu 0